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

Jump to bottom

Properly escape regex string literals #170

Merged
merged 1 commit into from
Feb 15, 2024
Merged

Properly escape regex string literals #170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions cppman/formatter/cppreference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ def member_type_function(g):
tail = ' ' + spectag.group(2)

cppvertag = re.search(
'^(.*?)(\[(?:(?:since|until) )?C\+\+\d+\]\s*(,\s*)?)+$', head)
r'^(.*?)(\[(?:(?:since|until) )?C\+\+\d+\]\s*(,\s*)?)+$', head)
if cppvertag:
head = cppvertag.group(1).strip()
tail = ' ' + cppvertag.group(2)
Expand Down Expand Up @@ -117,7 +117,7 @@ def member_type_function(g):
# Group t-lines
(r'<span></span>', r'', re.S),
(r'<span class="t-lines">(?:<span>.+?</span>.*)+</span>',
lambda x: re.sub('\s*</span><span>\s*', r', ', x.group(0)), re.S),
lambda x: re.sub(r'\s*</span><span>\s*', r', ', x.group(0)), re.S),
# Member type & function second col is group see basic_fstream for example
(r'<tr class="t-dsc">\s*?<td>((?:(?!</td>).)*?)</td>\s*?'
r'<td>((?:(?!</td>).)*?)<table[^>]*>((?:(?!</table>).)*?)</table>'
Expand Down
2 changes: 1 addition & 1 deletion cppman/formatter/tableparser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ def gen(self, fd, index=0, last=False, rowspan=None):
ci = 0
for i in range(total):
if i in rowspan:
fd.write('\^%s' % ('|' if i < total - 1 else ''))
fd.write(r'\^%s' % ('|' if i < total - 1 else ''))
if rowspan[i] == 1:
del rowspan[i]
else:
Expand Down
12 changes: 6 additions & 6 deletions cppman/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,7 +129,7 @@ def rebuild_index(self):
self.db_conn = sqlite3.connect(environ.index_db_re)
self.db_cursor = self.db_conn.cursor()
try:
self.add_url_filter('\.(jpg|jpeg|gif|png|js|css|swf|svg)$')
self.add_url_filter(r'\.(jpg|jpeg|gif|png|js|css|swf|svg)$')
self.set_follow_mode(Crawler.F_SAME_PATH)

sources = [('cplusplus.com', 'https://cplusplus.com/reference/', None),
Expand Down Expand Up @@ -399,10 +399,10 @@ def _extract_keywords(self, text):
for tr in x.find_all('tr'):
tds = tr.find_all('td')
if len(tds) == 2:
if re.match("\s*Type\s*", tds[0].get_text()):
if re.match(r"\s*Type\s*", tds[0].get_text()):
typedefTable = True
elif typedefTable:
res = re.search('^\s*(\S*)\s+.*$', tds[0].get_text())
res = re.search(r'^\s*(\S*)\s+.*$', tds[0].get_text())
if res and res.group(1):
names.append(res.group(1))
elif not typedefTable:
Expand All @@ -420,7 +420,7 @@ def _extract_keywords(self, text):
if e.name == "table":
for tr in e.find_all('tr'):
text = re.sub('\n', ' ', tr.get_text())
res = re.search('^.* (\S+)\s*=.*$', text)
res = re.search(r'^.* (\S+)\s*=.*$', text)
if res:
names.append(res.group(1))
# search for "Helper types" list
Expand All @@ -433,7 +433,7 @@ def _extract_keywords(self, text):
if e.name == "table":
for tr in e.find_all('tr'):
text = re.sub('\n', ' ', tr.get_text())
res = re.search('^.* (\S+)\s*=.*$', text)
res = re.search(r'^.* (\S+)\s*=.*$', text)
if res:
names.append(res.group(1))
return [html.unescape(n) for n in names]
Expand Down Expand Up @@ -583,7 +583,7 @@ def find(self, pattern):

results = self._search_keyword(pattern)

pat = re.compile('(.*?)(%s)(.*?)( \(.*\))?$' %
pat = re.compile(r'(.*?)(%s)(.*?)( \(.*\))?$' %
re.escape(pattern), re.I)

if results:
Expand Down