mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-01-19 15:04:01 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #11681 from alalek:fix_docs_bs4_spaces

Browse Source
This commit is contained in:
Alexander Alekhin 2018-06-04 16:15:45 +00:00
commit 9c2b924dfc
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
doc/tools/html_functions.py
View File

@ -3,6 +3,7 @@ import sys
import logging
import os
import re
from pprint import pprint
import traceback
@ -17,12 +18,20 @@ except ImportError:
def load_html_file(file_dir):
""" Uses BeautifulSoup to load an html """
with open(file_dir, 'rb') as fp:
soup = BeautifulSoup(fp, 'html.parser')
data = fp.read()
if os.name == 'nt' or sys.version_info[0] == 3:
data = data.decode(encoding='utf-8', errors='strict')
data = re.sub(r'(\>)([ ]+)', lambda match: match.group(1) + ('!space!' * len(match.group(2))), data)
data = re.sub(r'([ ]+)(\<)', lambda match: ('!space!' * len(match.group(1))) + match.group(2), data)
if os.name == 'nt' or sys.version_info[0] == 3:
data = data.encode('utf-8', 'ignore')
soup = BeautifulSoup(data, 'html.parser')
return soup
def update_html(file, soup):
s = str(soup)
if os.name == 'nt' or sys.version_info[0] == 3: # if Windows
s = s.replace('!space!', ' ')
if os.name == 'nt' or sys.version_info[0] == 3:
s = s.encode('utf-8', 'ignore')
with open(file, 'wb') as f:
f.write(s)