Skip to content
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

Removing unicode characters from search index #151

Merged
merged 3 commits into from
May 6, 2020
Merged

Removing unicode characters from search index #151

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0a435fd
Removing unicode characters from search index
May 5, 2020
51cc32f
Adding issue 151 to changelog
May 6, 2020
9c3b0b5
Adding issue 150 to changelog
May 6, 2020
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
18 changes: 14 additions & 4 deletions modules/search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ def generate_index():
if not os.path.isdir(config.web_directory):
os.makedirs(config.web_directory)

json.dump(index, open(os.path.join(config.web_directory, "index.json"), mode="w", encoding="utf8"), indent=2)
json.dump(index, open(os.path.join(config.web_directory, "index.json"), mode="w", encoding="utf-8"), indent=2)

if (config.subdirectory):
# update search base url to subdirectory
Expand All @@ -50,9 +50,19 @@ def skipline(line):
if skip in line: return True
return False

def clean_line(line):
"""clean unicode spaces from line"""
# Replace unicode spaces
line = line.replace(u"\u00a0", " ")
line = line.replace(u"\u202f", " ")
line = line.replace(" ", " ")
line = line.replace("&nbsp", " ")

return line

def clean(filepath):
"""clean the file of all HTML tags and unnecessary data"""
f = open(filepath, mode="r", encoding="utf8")
f = open(filepath, mode="r", encoding="utf-8")
lines = f.readlines()
f.close()

Expand All @@ -61,8 +71,8 @@ def clean(filepath):
skipindex = False
indexing = False
for line in lines:
if (not skipline(line)) and indexing:
content += line + "\n"
if (not skipline(line)) and indexing:
content += clean_line(line) + "\n"
if "<!--start-indexing-for-search-->" in line:
indexing = True
if "<!--stop-indexing-for-search-->" in line:
Expand Down