Skip to content

Hotfix/register huge text #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sasaujp wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Hotfix/register huge text #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d8a40ec
zipの構造によってuploadに失敗する場合があるのを修正
sasaujp Jan 25, 2017
6de69d7
huge text stream
sasaujp Apr 14, 2017
ed299f6
fix return None
sasaujp Apr 18, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 12 additions & 9 deletions src/common/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ def get_disk_info():
disk_info.append({
'mount': row[mounted_on_index],
'size': calculate_human_readable_filesize(st.f_frsize * st.f_blocks),
'used': calculate_human_readable_filesize(st.f_frsize * (st.f_blocks-st.f_bfree)),
'used': calculate_human_readable_filesize(st.f_frsize * (st.f_blocks - st.f_bfree)),
'avail': calculate_human_readable_filesize(st.f_frsize * st.f_favail)
})
return disk_info
Expand Down Expand Up @@ -228,11 +228,14 @@ def get_images_in_random_order(path, num):
return ret


def get_text_sample(path, character_num=-1):
raw_text = open(path).read()
encoding = nkf.guess(raw_text)
text = raw_text.decode(encoding)
if character_num > -1:
return text[0:character_num]
else:
return text
def get_text_sample(path, character_num=100):
text = ''
with open(path) as fp:
for row in fp:
text += row.strip()
if len(text) > character_num:
break
else:
text = text[:character_num]
encoding = nkf.guess(text)
return text.decode(encoding)
7 changes: 3 additions & 4 deletions src/db_models/datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,10 +194,9 @@ def save_uploaded_data(self, uploaded_file, save_raw_file_to, save_to):
if ('__MACOSX' in file_name) or ('.DS_Store' in file_name):
continue
temp_path = os.path.join(extract_to, file_name)
if not os.path.basename(file_name):
if not os.path.exists(temp_path):
os.makedirs(temp_path.encode(encoding='utf-8'))
category_num += 1
if not os.path.exists(os.path.dirname(temp_path)):
os.makedirs(temp_path.encode(encoding='utf-8'))
category_num += 1
else:
temp, ext = os.path.splitext(temp_path)
ext = ext.lower()
Expand Down